Incentives for Responsiveness, Instrumental Control and Impact
Ryan Carey, Eric Langlois, Chris van Merwijk, Shane Legg, Tom Everitt — 2020-01-20 — DeepMind — arXiv
Summary
Introduces formal theoretical framework using causal graphs to characterize agent incentives for responsiveness, instrumental control, and impact, establishing sound and complete graphical criteria for each concept.
Source
- Link: https://arxiv.org/abs/2001.07118
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- control — Black-box safety (understand and control current model behaviour) / Iterative alignment